Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Russian suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Neighbors
    -0.08
    Slim
    -0.08
    rey
    -0.07
    Moz
    -0.07
    Ther
    -0.07
    Experiment
    -0.07
     lur
    -0.07
    Mont
    -0.07
    Sir
    -0.07
    Save
    -0.07
    POSITIVE LOGITS
     begun
    0.08
    力量
    0.08
     disorders
    0.08
     Disorders
    0.08
    ↵    ↵    ↵
    0.08
     सं
    0.07
     power
    0.07
    ിറ്റ
    0.07
    ൂ
    0.07
     درجات
    0.07
    Act Density 0.057%

    No Known Activations